{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FZXDSYR2HEYPMURJAZNQBIKT4B","short_pith_number":"pith:FZXDSYR2","canonical_record":{"source":{"id":"2310.01765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T03:13:23Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"3b0c2c821b5826e64047b2919b49b6553b703f9a9fefd7be639ad5096c0d8327","abstract_canon_sha256":"e4b8198db155e46b01944e9a5c49f75efb697eada34cb3a0f00a0c1d73ea2163"},"schema_version":"1.0"},"canonical_sha256":"2e6e39623a3930f65229065b00a153e05433e37f5379edcae2743563951b476d","source":{"kind":"arxiv","id":"2310.01765","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01765","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01765v2","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01765","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"pith_short_12","alias_value":"FZXDSYR2HEYP","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"pith_short_16","alias_value":"FZXDSYR2HEYPMURJ","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"pith_short_8","alias_value":"FZXDSYR2","created_at":"2026-07-05T08:25:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FZXDSYR2HEYPMURJAZNQBIKT4B","target":"record","payload":{"canonical_record":{"source":{"id":"2310.01765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T03:13:23Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"3b0c2c821b5826e64047b2919b49b6553b703f9a9fefd7be639ad5096c0d8327","abstract_canon_sha256":"e4b8198db155e46b01944e9a5c49f75efb697eada34cb3a0f00a0c1d73ea2163"},"schema_version":"1.0"},"canonical_sha256":"2e6e39623a3930f65229065b00a153e05433e37f5379edcae2743563951b476d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:28.955149Z","signature_b64":"CytR0w/VIIS873P99x4fiGGySobpHwGDRWehBYYgJ/57SE9o3h5h69MgoobGskAxElBCUqcxpT2uyczIbWnhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6e39623a3930f65229065b00a153e05433e37f5379edcae2743563951b476d","last_reissued_at":"2026-07-05T08:25:28.954676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:28.954676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.01765","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z6WnImJ2A0U3+mBjlCPWM/RXYu1xJvV4FU+8QeKa0hCFgO84VxxooVFPg7cRGh0xfULBpfHVAQmiYXgVob78Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:45:54.254669Z"},"content_sha256":"c48dcd9fe5774f79202f526590586b36b05a40ec27c3dd49028294af7e24b4cf","schema_version":"1.0","event_id":"sha256:c48dcd9fe5774f79202f526590586b36b05a40ec27c3dd49028294af7e24b4cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FZXDSYR2HEYPMURJAZNQBIKT4B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Cleaning and Machine Learning: A Systematic Literature Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Amin Nikanjam, Dmytro Humeniuk, Foutse Khomh, Nafisa Ahmed, Pierre-Olivier C\\^ot\\'e","submitted_at":"2023-10-03T03:13:23Z","abstract_excerpt":"Context: Machine Learning (ML) is integrated into a growing number of systems for various applications. Because the performance of an ML model is highly dependent on the quality of the data it has been trained on, there is a growing interest in approaches to detect and repair data errors (i.e., data cleaning). Researchers are also exploring how ML can be used for data cleaning; hence creating a dual relationship between ML and data cleaning. To the best of our knowledge, there is no study that comprehensively reviews this relationship. Objective: This paper's objectives are twofold. First, it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01765","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.01765/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9nW/v8CaJ/KxsRchqQ9XNivvRDg+5ocFIGLD7eRCtR8ZuWGbj1taYasPF/AOAehMagWr7GQG6NVbzM52IiW3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:45:54.255035Z"},"content_sha256":"57e0b2cb03b300313c36545e6839668c0d19b241dabe12cb1f2e6afd1817a438","schema_version":"1.0","event_id":"sha256:57e0b2cb03b300313c36545e6839668c0d19b241dabe12cb1f2e6afd1817a438"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/bundle.json","state_url":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T03:45:54Z","links":{"resolver":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B","bundle":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/bundle.json","state":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FZXDSYR2HEYPMURJAZNQBIKT4B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e4b8198db155e46b01944e9a5c49f75efb697eada34cb3a0f00a0c1d73ea2163","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T03:13:23Z","title_canon_sha256":"3b0c2c821b5826e64047b2919b49b6553b703f9a9fefd7be639ad5096c0d8327"},"schema_version":"1.0","source":{"id":"2310.01765","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01765","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01765v2","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01765","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"pith_short_12","alias_value":"FZXDSYR2HEYP","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"pith_short_16","alias_value":"FZXDSYR2HEYPMURJ","created_at":"2026-07-05T08:25:28Z"},{"alias_kind":"pith_short_8","alias_value":"FZXDSYR2","created_at":"2026-07-05T08:25:28Z"}],"graph_snapshots":[{"event_id":"sha256:57e0b2cb03b300313c36545e6839668c0d19b241dabe12cb1f2e6afd1817a438","target":"graph","created_at":"2026-07-05T08:25:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.01765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Context: Machine Learning (ML) is integrated into a growing number of systems for various applications. Because the performance of an ML model is highly dependent on the quality of the data it has been trained on, there is a growing interest in approaches to detect and repair data errors (i.e., data cleaning). Researchers are also exploring how ML can be used for data cleaning; hence creating a dual relationship between ML and data cleaning. To the best of our knowledge, there is no study that comprehensively reviews this relationship. Objective: This paper's objectives are twofold. First, it ","authors_text":"Amin Nikanjam, Dmytro Humeniuk, Foutse Khomh, Nafisa Ahmed, Pierre-Olivier C\\^ot\\'e","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T03:13:23Z","title":"Data Cleaning and Machine Learning: A Systematic Literature Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01765","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c48dcd9fe5774f79202f526590586b36b05a40ec27c3dd49028294af7e24b4cf","target":"record","created_at":"2026-07-05T08:25:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e4b8198db155e46b01944e9a5c49f75efb697eada34cb3a0f00a0c1d73ea2163","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T03:13:23Z","title_canon_sha256":"3b0c2c821b5826e64047b2919b49b6553b703f9a9fefd7be639ad5096c0d8327"},"schema_version":"1.0","source":{"id":"2310.01765","kind":"arxiv","version":2}},"canonical_sha256":"2e6e39623a3930f65229065b00a153e05433e37f5379edcae2743563951b476d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e6e39623a3930f65229065b00a153e05433e37f5379edcae2743563951b476d","first_computed_at":"2026-07-05T08:25:28.954676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:28.954676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CytR0w/VIIS873P99x4fiGGySobpHwGDRWehBYYgJ/57SE9o3h5h69MgoobGskAxElBCUqcxpT2uyczIbWnhCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:28.955149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01765","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c48dcd9fe5774f79202f526590586b36b05a40ec27c3dd49028294af7e24b4cf","sha256:57e0b2cb03b300313c36545e6839668c0d19b241dabe12cb1f2e6afd1817a438"],"state_sha256":"eebc7d556f6ac5cb8fabf77dfa16f2ef2f9a2ef7ba14e86ba613f4cad87b94e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iABpucgUtD3ul5UPknHjwgkbAj13ousUAc8xKExpthFCGe68dyMSe9/reQ85V3TRJt3YGSVmXGhbnn0vSeZ/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:45:54.256975Z","bundle_sha256":"e094df7399898d8a127615cca5d1e8aa987689d638e4de6a273b3c144f9fc16f"}}